Seedance 2.5 reference-anchored test: 20 s monochrome fog scene with two big-eyed figures that reads as rendered characters
Black-and-white fog: two small pointed-eared figures in a twisted tree hollow, backs of heads, a drifting light, close faces with large round eyes and two small figures fading into fog.
Task: Two small pale-eyed figures in a gothic hollow tree, asked for as live-action dark fantasy with practical makeup on real performers.
Outcome: succeeded
0.84 s: Two small figures with large pale eyes and pointed ears stand in a twisted tree hollow, fog around.
4.18 s: Backs of two heads in close view, a small light in the mist.
9.20 s: Front view: both faces with large white eyes.
12.54 s: Close on one face.
14.21 s: Close on the pair.
15.88 s: Backs of two heads again.
17.56 s: Two small figures in fog.
19.23 s: The figures faint in fog.
Intent vs result: The prompt asked for live-action dark fantasy with practical makeup on real performers; the sampled frames read as rendered stylised characters with large round eyes, not as live performers.
Publication update (2026-10-29): the founder has now cleared public use of this output, including incorporated input likenesses and soundtrack. Earlier rights/likeness holds described above are resolved by that confirmation. Reference-input files remain private. Audio remains not listened to; visual observations cover sampled frames only.
Structured fields
{
"inputs": [
{
"description": "1 linked image input(s) recorded in the generation metadata (details withheld)."
}
],
"run_at": "2026-08-10T21:57:22Z",
"metrics": [
{
"name": "output_duration",
"unit": "s",
"value": 20.064
},
{
"name": "resolution",
"value": "1280x720"
},
{
"name": "frame_rate",
"value": "24/1"
},
{
"name": "scene_detector_transitions_thr0.30",
"value": 4
},
{
"name": "black_intervals",
"value": "none"
}
],
"procedure": "Seedance 2.5, one reference still used as the look-and-world anchor, a long structured prompt (one subject, a setting and a shot-by-shot format) that asks for a large-format anamorphic-cinema look, 20 s, 16:9, audio requested, no seed set. One of a run of tests on 10-11 August 2026 (UTC) that each pair the same kind of reference still with a different subject and mood. Sampled inspection: 12 timestamped frames from 0.84 s to 19.23 s of a 20.06 s file, plus ffmpeg scene detection at threshold 0.30 and blackdetect.",
"parameters": {
"seed": "unset",
"model": "seedance_2_5 (label in job metadata)",
"multi_shots": false,
"aspect_ratio": "16:9",
"audio_requested": true,
"resolution_label": "720p",
"requested_duration_s": 20
},
"limitations": [
"Sampled visual inspection from timestamped frames (contact sheets), not full real-time playback; motion smoothness, micro-timing and lip-sync are unrated.",
"Audio was not listened to; the file has an audio track but sound, dialogue and music are unassessed.",
"Prompt intent is taken from private job metadata and summarised here only in general terms; the founder's taste and intent for each test are unknown.",
"Single historical generation without a fixed seed; not a controlled benchmark and not validation of any current product or pipeline.",
"Requested live-action look not apparent in the sampled frames."
],
"artifact_ids": [
"ast_01M64WMX8DX3YP69FS2TPT562H"
]
}Evidence claims
- [sourced_fact] Timestamped observations above come from viewing 12 sampled frames of the output (sampled visual inspection, not full playback).
- [upstream_claim] The generation was run by the founder in an earlier test period; H01 did not run or reproduce it.
- [inference] A live-action request may not override a strongly stylised reference; compare frames with the intended look.
Rights
| component | license | hosting | redistribution | modification | training | Evidence and notes |
|---|---|---|---|---|---|---|
| documentation | unknown | permitted | permitted | unknown | unknown | Original analysis written by H01 (an AI agent) for Veyrul from private viewing; no third-party text, frames or audio reproduced. |
| media | unknown | permitted | permitted | unknown | unknown | Founder confirmed public use of all these Higgsfield outputs on 2026-10-29, including incorporated reference inputs, likenesses and soundtrack. Audio has not been listened to; permission does not establish listening or independent review. |